BIM-PoseNet: Indoor camera localisation using a 3D indoor model and deep learning from synthetic images

被引:86
作者
Acharya, Debaditya [1 ]
Khoshelham, Kourosh [1 ]
Winter, Stephan [1 ]
机构
[1] Univ Melbourne, Dept Infrastruct Engn, Parkville, Vic 3010, Australia
关键词
Indoor localisation; Camera pose regression; 3D building models; BIM; Deep learning; Synthetic images;
D O I
10.1016/j.isprsjprs.2019.02.020
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
The ubiquity of cameras built in mobile devices has resulted in a renewed interest in image-based localisation in indoor environments where the global navigation satellite system (GNSS) signals are not available. Existing approaches for indoor localisation using images either require an initial location or need first to perform a 3D reconstruction of the whole environment using structure-from-motion (SfM) methods, which is challenging and time-consuming for large indoor spaces. In this paper, a visual localisation approach is proposed to eliminate the requirement of image-based reconstruction of the indoor environment by using a 3D indoor model. A deep convolutional neural network (DCNN) is fine-tuned using synthetic images obtained from the 3D indoor model to regress the camera pose. Results of the experiments indicate that the proposed approach can be used for indoor localisation in real-time with an accuracy of approximately 2 m.
引用
收藏
页码:245 / 258
页数:14
相关论文
共 61 条
[1]  
Acharya D., 2018, Proceedings of the 5th Annual Conference of Research, page, V4, P33
[2]   BIM-Tracker: A model-based visual tracking approach for indoor localisation using a 3D building model [J].
Acharya, Debaditya ;
Ramezani, Milad ;
Khoshelham, Kourosh ;
Winter, Stephan .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2019, 150 :157-171
[3]  
[Anonymous], 2009, PROC IEEE C COMPUT V
[4]  
[Anonymous], 2017, P 4 ANN C RES LOC
[5]  
[Anonymous], 2018, PROC WORKSHOP LEARN
[6]  
[Anonymous], P IEEE INT C COMP VI
[7]  
[Anonymous], 2017, P COMP VIS PATT REC
[8]  
[Anonymous], INT ARCH PHOTOGRAMM
[9]  
[Anonymous], 2012, INDOOR POSITIONING T
[10]  
[Anonymous], IEEE T PATTERN ANAL